Effective monitoring of water quality is critical for water safety. In particular, online monitoring based on modeling is useful in several applications such as process assessment, hazardous event detection or common fault diagnostics in the water processes. Soft sensors have lately established themselves as a good alternative for different tasks of process control such as the acquisition of critical process variables and process monitoring. In this paper, we introduce a dynamic method for predicting turbidity in drinking water. The goals of the work were to construct a dynamic real-time data-driven model to predict the turbidity in treated water and to find the most significant variables affecting turbidity. Both linear and non-linear regression methods are used in modeling. Our results show that the static linear or non-linear model (r = 0.40 and r = 0.52, respectively) is not able to follow the changes in turbidity, whereas the dynamic method can produce a reasonable estimate for turbidity (r = 0.75 for the dynamic linear and r = 0.86 for the dynamic non-linear model). In conclusion, the data analysis procedure seems to provide an efficient means of modeling the water treatment process online and of defining the most affecting variables.
Dynamic soft sensors for detecting factors affecting turbidity in drinking water
Petri Juntunen, Mika Liukkonen, Markku J. Lehtola, Yrjö Hiltunen; Dynamic soft sensors for detecting factors affecting turbidity in drinking water. Journal of Hydroinformatics 1 April 2013; 15 (2): 416–426. doi: https://doi.org/10.2166/hydro.2012.052
Download citation file:
Close
Petri Juntunen, Mika Liukkonen, Markku J. Lehtola, Yrjö Hiltunen; Dynamic soft sensors for detecting factors affecting turbidity in drinking water. Journal of Hydroinformatics 1 April 2013; 15 (2): 416–426. doi: https://doi.org/10.2166/hydro.2012.052
Download citation file:
Close
Impact Factor 1.728
CiteScore 3.5 • Q2
Cited by
Subscribe to Open
This paper is Open Access via a Subscribe to Open model. Individuals can help sustain this model by contributing the cost of what would have been author fees. Find out more here.